Step 3.7 Flash
by StepFun · stepfun/step-3.7-flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
- Input / 1M tokens
- $0.20
- Output / 1M tokens
- $1.15
- Context
- 262K
Specs
| Input price | $0.20 / 1M tokens |
|---|---|
| Output price | $1.15 / 1M tokens |
| Cached input | $0.04 / 1M tokens |
| Context window | 262K tokens |
| Max output | 230K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | May 28, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
2 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Novita | fp8 | 262K | 256K | $0.20 | $1.15 | $0.04 | 100% | 5.10 s | 28 tok/s | Normal | |
| StepFun | fp8 | 256K | 230K | $0.20 | $1.15 | $0.04 | 100% | 5.10 s | 39 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#44
by tokens, Oct 29, 2026
73.4B
tokens that day · 7 days New
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- StepFun
Step 5 Preview
- Input
- $1.00
- Output
- $2.70
- Context
- 1.05M
- StepFun
Step 3.5 Flash
- Input
- $0.10
- Output
- $0.30
- Context
- 262K
- OpenAI
GPT-5.6 Luna
- Input
- $0.20
- Output
- $1.20
- Context
- 1.05M
- Google
Gemma 4 31B
- Input
- $0.20
- Output
- $0.40
- Context
- 262K
- OpenAI
GPT-5.6 Luna Pro
- Input
- $0.20
- Output
- $1.20
- Context
- 1.05M
- NVIDIA
Nemotron 3.5 Content Safety
- Input
- $0.20
- Output
- $0.20
- Context
- 131K